Screen scrape using php and fopen [duplicate] - php

Question

This question already has an answer here:
Closed 10 years ago.
Possible Duplicate:
Screen scapingin in php using file_get_contents
Can anyone help me.. I am trying to scrape Hotel reviews from LateRooms.com dont tell me its a bad idea because I already have permission as an affiliate
My code:
<?php
header('content-type: text/plain');
$contents = file_get_contents('http://www.laterooms.com/en/hotel-reviews/238902_the-westfield-bb-sandown.aspx');
$contents = preg_replace('/\s(1,)/', ' ', $contents);
print $contents . "\n";
$records = preg_split('/<div id="review/', $contents);
for ($ix = 1; $ix < count($records); $ix++) {
$tmp = $records[$ix];
preg_match('/id="review"/', $tmp, $match_reviews);
print_r($match_reviews);
exit();
}
?>
This works really well the only problem is that It pulls in the whole page of code and doesnt match the div id 'review'
Thanks in advance

Answer 1

function file_get_contents_curl($url){
$ch = curl_init();
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
$data = curl_exec($ch);
curl_close($ch);
return $data;
}
function DOMinnerHTML($element){
$innerHTML = "";
$children = $element->childNodes;
foreach ($children as $child)
{
$tmp_dom = new DOMDocument();
$tmp_dom->appendChild($tmp_dom->importNode($child, true));
$innerHTML.=trim($tmp_dom->saveHTML());
}
return $innerHTML;
}
$url = 'http://www.laterooms.com/en/hotel-reviews/238902_the-westfield-bb-sandown.aspx';
$html = file_get_contents_curl($url);
//parsing begins here:
$doc = new DOMDocument();
#$doc->loadHTML($html);
$div_elements = $doc->getElementsByTagName('div');
if ($div_elements->length <> 0){
foreach ($div_elements as $div_element) {
if ($div_element->getAttribute('class') == 'review newReview'){
$reviews[] = DOMinnerHTML($div_element);
}
}
}
print_r($reviews);
Try this, it will return all reviews. You can refine the content as per your requirement.